卷积神经网络(基础篇):
下采样(Subsampling):通道数不变,减少数据量,降低运算需求。
做这个卷积:
网络:
最大池化层(MaxPooling):通道数不变,图像大小缩成原来的一半,没有权重。
代码:
import torchfrom torchvision import transformsfrom torchvision import datasetsfrom torch.utils.data import DataLoaderimport torch.nn.functional as Fimport torch.optim as optim# prepare datasetbatch_size = 64transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)# design model using classclass Net(torch.nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5) self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=5) self.pooling = torch.nn.MaxPool2d(2) self.fc = torch.nn.Linear(320, 10) def forward(self, x): # flatten data from (n,1,28,28) to (n, 784) batch_size = x.size(0) #求batchsize x = F.relu(self.pooling(self.conv1(x))) #卷积、池化、激活 x = F.relu(self.pooling(self.conv2(x))) x = x.view(batch_size, -1) # -1 此处自动算出的是320;view的目的就是变成全连接网络需要的格式。flatten x = self.fc(x) return xmodel = Net()device = torch.device("cuda" if torch.cuda.is_available() else "cpu") #如果你有GPU,这两行的意思就是用GPU跑model.to(device) #没有GPU的话这两行可以不写(写上也无妨)# construct loss and optimizercriterion = torch.nn.CrossEntropyLoss()optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# training cycle forward, backward, updatedef train(epoch): running_loss = 0.0 for batch_idx, data in enumerate(train_loader, 0): inputs, target = data inputs, target = inputs.to(device), target.to(device)#把数据迁移到GPU上,如果没有GPU,这行可以不写 optimizer.zero_grad() outputs = model(inputs) loss = criterion(outputs, target) loss.backward() optimizer.step() running_loss += loss.item() if batch_idx % 300 == 299: print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300)) running_loss = 0.0def test(): correct = 0 total = 0 with torch.no_grad(): for data in test_loader: images, labels = data images, labels = images.to(device), labels.to(device) #如果没有GPU,这行可以不写 outputs = model(images) _, predicted = torch.max(outputs.data, dim=1) total += labels.size(0) correct += (predicted == labels).sum().item() print('accuracy on test set: %d %% ' % (100 * correct / total))if __name__ == '__main__': for epoch in range(10): train(epoch) test()
经过10轮的训练后,模型的准确度达到了98%,用线性模型是97%。
卷积神经网络(提高篇):
Inception Module:
Concatenate:把张量拼接到一块;
Average Pooling:均值池化;
1×1卷积:将来的卷积核是1×1,个数取决于输出张量的通道。
1×1卷积作用:(主要就是降维)
部分模块代码:
代码:
import torchimport torch.nn as nnfrom torchvision import transformsfrom torchvision import datasetsfrom torch.utils.data import DataLoaderimport torch.nn.functional as Fimport torch.optim as optim# prepare datasetbatch_size = 64transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]) # 归一化,均值和方差train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)# design model using classclass InceptionA(nn.Module): def __init__(self, in_channels): super(InceptionA, self).__init__() self.branch1x1 = nn.Conv2d(in_channels, 16, kernel_size=1) self.branch5x5_1 = nn.Conv2d(in_channels, 16, kernel_size=1) self.branch5x5_2 = nn.Conv2d(16, 24, kernel_size=5, padding=2) self.branch3x3_1 = nn.Conv2d(in_channels, 16, kernel_size=1) self.branch3x3_2 = nn.Conv2d(16, 24, kernel_size=3, padding=1) self.branch3x3_3 = nn.Conv2d(24, 24, kernel_size=3, padding=1) self.branch_pool = nn.Conv2d(in_channels, 24, kernel_size=1) def forward(self, x): branch1x1 = self.branch1x1(x) branch5x5 = self.branch5x5_1(x) branch5x5 = self.branch5x5_2(branch5x5) branch3x3 = self.branch3x3_1(x) branch3x3 = self.branch3x3_2(branch3x3) branch3x3 = self.branch3x3_3(branch3x3) branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1) branch_pool = self.branch_pool(branch_pool) outputs = [branch1x1, branch5x5, branch3x3, branch_pool] return torch.cat(outputs, dim=1) # b,c,w,h c对应的是dim=1class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(1, 10, kernel_size=5) self.conv2 = nn.Conv2d(88, 20, kernel_size=5) # 88 = 24x3 + 16 self.incep1 = InceptionA(in_channels=10) # 与conv1 中的10对应 self.incep2 = InceptionA(in_channels=20) # 与conv2 中的20对应 self.mp = nn.MaxPool2d(2) self.fc = nn.Linear(1408, 10) def forward(self, x): in_size = x.size(0) x = F.relu(self.mp(self.conv1(x))) #通道变为10 x = self.incep1(x) #88 x = F.relu(self.mp(self.conv2(x))) #20 x = self.incep2(x) #88 x = x.view(in_size, -1) x = self.fc(x) return xmodel = Net()# construct loss and optimizercriterion = torch.nn.CrossEntropyLoss()optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# training cycle forward, backward, updatedef train(epoch): running_loss = 0.0 for batch_idx, data in enumerate(train_loader, 0): inputs, target = data optimizer.zero_grad() outputs = model(inputs) loss = criterion(outputs, target) loss.backward() optimizer.step() running_loss += loss.item() if batch_idx % 300 == 299: print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300)) running_loss = 0.0def test(): correct = 0 total = 0 with torch.no_grad(): for data in test_loader: images, labels = data outputs = model(images) _, predicted = torch.max(outputs.data, dim=1) total += labels.size(0) correct += (predicted == labels).sum().item() print('accuracy on test set: %d %% ' % (100 * correct / total))if __name__ == '__main__': for epoch in range(10): train(epoch) test()
Residual Network:
?:保持输入和输出大小相同。
代码:
import torchimport torch.nn as nnfrom torchvision import transformsfrom torchvision import datasetsfrom torch.utils.data import DataLoaderimport torch.nn.functional as Fimport torch.optim as optim# prepare datasetbatch_size = 64transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]) # 归一化,均值和方差train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)# design model using classclass ResidualBlock(nn.Module): def __init__(self, channels): super(ResidualBlock, self).__init__() self.channels = channels self.conv1 = nn.Conv2d(channels, channels, kernel_size=3, padding=1) self.conv2 = nn.Conv2d(channels, channels, kernel_size=3, padding=1) def forward(self, x): y = F.relu(self.conv1(x)) y = self.conv2(y) return F.relu(x + y)class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(1, 16, kernel_size=5) self.conv2 = nn.Conv2d(16, 32, kernel_size=5) # 88 = 24x3 + 16 self.rblock1 = ResidualBlock(16) self.rblock2 = ResidualBlock(32) self.mp = nn.MaxPool2d(2) self.fc = nn.Linear(512, 10) # 暂时不知道1408咋能自动出来的 def forward(self, x): in_size = x.size(0) x = self.mp(F.relu(self.conv1(x))) x = self.rblock1(x) x = self.mp(F.relu(self.conv2(x))) x = self.rblock2(x) x = x.view(in_size, -1) x = self.fc(x) return xmodel = Net()# construct loss and optimizercriterion = torch.nn.CrossEntropyLoss()optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# training cycle forward, backward, updatedef train(epoch): running_loss = 0.0 for batch_idx, data in enumerate(train_loader, 0): inputs, target = data optimizer.zero_grad() outputs = model(inputs) loss = criterion(outputs, target) loss.backward() optimizer.step() running_loss += loss.item() if batch_idx % 300 == 299: print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300)) running_loss = 0.0def test(): correct = 0 total = 0 with torch.no_grad(): for data in test_loader: images, labels = data outputs = model(images) _, predicted = torch.max(outputs.data, dim=1) total += labels.size(0) correct += (predicted == labels).sum().item() print('accuracy on test set: %d %% ' % (100 * correct / total))if __name__ == '__main__': for epoch in range(10): train(epoch) test()
【番外:1.理论学习 2.阅读文献 3.复现经典 4.扩充视野】